1130 Commits (b34933d9ee3b61dbbd642fd02f244c36d0d14550)

Author	SHA1	Message	Date
石晓伟	04ea7cb069	modify the access level of anakin engine (#18015) ... test=develop	6 years ago
石晓伟	bce259e5bf	Update the Anakin interfaces for content-dnn and MLU (#17890) ... * update anakin-engine interfaces for content-dnn test=develop * support only-gpu mode of Anakin modify eltwise parse test=develop * modification for thread-safe test=develop * Integrated template instance test=develop * increase template parameters test=develop * support MLU predictor test=develop * update anakin cmake files test=develop * update TargetWrapper::set_device * update the initialization of anakin subgraph test=develop * use the default constructor of base class test=develop	6 years ago
Zhaolong Xing	4e8d5a034f	Light mem reuse strategy for inference. (#17925) ... * fix: when use the load model from memory mode, the RAM occupy is high test=develop * ligth mem reuse test=develop * fix cpplint test=develop	6 years ago
mozga-intel	c1379bf238	[NGraph] Bert model for a capi, ngraph's support test=develop (#17844)	6 years ago
石晓伟	d008260fa8	update the initialization of anakin subgraph (#17880) ... test=develop	6 years ago
Zhaolong Xing	ae576f3c68	fix: when use the load model from memory mode, the RAM occupy is high (#17788) ... test=develop	6 years ago
翟飞跃	993c703bcc	INT8 MKL-DNN v2 integrate to slim (#17634) ... * refactor PR 16865 * delete mergetool files * test=develop * test=develop * test=develop * test=develop * create dir for int8 model before call SaveOptimModel * test=develop * mkldnn int8 only support linux; test=develop * refine code; test=develop * remove comment; test=develop * refine code; test=develop * fix bug; test=develop * add exception for mkldnn_post_training_strategy * reuse int8v2 CAPI dataset; test=develop * fix accuracy check bug; test=develop * remove tab * convert files to unix format * test=develop * reduce CI time;test=develop * reduce CI time and refine code;test=develop * refine comment; test=develop * add cmake FLAGS;test=develop * remove predict_num;test=develop	6 years ago
Tao Luo	e089e454a1	make omp thread num default 1 after inference run (#17801) ... test=develop	6 years ago
Tao Luo	b4b169467b	add fc_mkldnn_pass in compare_mkldnn (#17712) ... test=develop	6 years ago
Zhaolong Xing	4337009b92	fix trt ci timeout error (#17701) ... test=develop	6 years ago
mozga-intel	5eb81fe595	Capi for a ngraph engine (#17037)	6 years ago
lidanqing	04b6c29ee0	Improve mobilenetv2 INT8 performance by using INT8 relu as post-op (#17570) ... * add INT8 conv+relu6 fuse and enbale mobilentv2 INT8 test test=develop * change fasle and 0.0 to fuse_brelu and brelu_threshold test=develop change the "fuse_relu||fuse_brelu" to "unsigned_output" test=develop * Use relu instead of brelu as INT8 post-op because INT8 brelu is not enabled in mkldnn v0.18 test=develop * continuous-integration fix test=develop	6 years ago
Jacek Czaja	6d8075ecef	[MKL-DNN] conv_transpose mkldnn bias pass (#17644) ... * - changes to graph detector - Changes to pass - Added ut for new pass - use_pass - Added pass to mkldnn passes - fix to registration - improved verbose messaging for conv bias passes - Lint fixes test=develop * - Lint fixes test=develop	6 years ago
Sylwester Fraczek	96845d2168	add Concat quantization (#17448) ... * add Concat quantization add unit test for quantizing concat fix for wrong value when the input is not in map of calculated scales add use_quantizer to concat_op.cc add scale_algo rules for concat test=develop * missing fix for multiple inputs quantize-squash * wojtuss review fix: adding comment test=develop	6 years ago
Zhen Wang	8bd651b7ed	Fix the bug in the AnalysisPredictor and add more directions about io APIs. (#17639) ... * fix the bug that sub_scope_ may be null in AnalysisPredictor::Run. * add more directions about io APIs' docs. * update the API.spec. test=develop test=document_preview	6 years ago
Zeng Jinle	4aa931dd85	Code clean of Allocator (#17602) ... * Revert "Revert "Fix allocator bug"" This reverts commit 174d0d0b90. * Revert "fix travis ci" This reverts commit 5656fa9f7c. test=develop * add inlined_vector.h, test=develop * add inlined_vector_test,test=develop * clean code of allocator,test=develop * delete zero_size_allocator.h,test=develop * fix failed unittest,test=develop	6 years ago
Zhaolong Xing	61221ebc28	TRT: Support set dynamic range in int8 mode. (#17524) ... * fluid int8 train and trt int8 predict align. trt int8 predict init op converter * 2. align fluid int8 train and trt int8 inference. enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass. * 3. add delete_quant_dequant_pass for trt test=develop * 4. add the missing file test=develop * 5. i modify the c++ interface, but forget to modify the pybind code fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop	6 years ago
Michał Gallus	0c39b97b4e	[MKL-DNN] Add Fully Connected Op for inference only(#15226) ... * fuse mul and elementwise add to fc * Reimplement the FC forward operator * Fix FC MKLDNN integration by transposing weights * Add FC MKLDNN Pass test=develop * FC MKLDNN Pass: change memcpy to std::copy * Fix MKLDNN FC handling of mismatch input and weights dims * Lower tolerance for MKL-DNN in resnet50 test test=develop * Adjust FC to support MKLDNN Op placement test=develop * Adjust Placement Op to set use_mkldnn attribute for graph test=develop * MKLDNN FC: fix weights format so that gemm version is called test=develop * FC MKLDNN: Remove tolerance decrease from tester_helper * FC MKL-DNN: Refactor the code, change input reorder to weight reorder * MKL-DNN FC: Introduce operator caching test=develop * FC MKL-DNN: Fix the tensor type in ExpectedKernelType test=develop * FC MKL-DNN: fix style changes test=develop * FC MKL-DNN: fallback to native on non-supported dim sizes test=develop * FC MKLDNN: fix CMake paths test=develop * FC MKLDNN: Refine placement pass graph mkldnn attribute test=develop * Fix Transpiler error for fuse_conv_eltwise test=develop * Fix missing STL includes in files test=develop * FC MKL-DNN: Enable new output size computation Also, refine pass to comply with newest interface. test=develop * FC MKL-DNN: enable only when fc_mkldnn_pass is enabled * FC MKL-DNN: Allow Weights to use oi or io format * FC MKL-DNN: Adjust UT to work with correct dims test=develop * Enable MKL DEBUG for resnet50 analyzer test=develop * FC MKL-DNN: Improve Hashing function test=develop * FC MKL-DNN: Fix shape for fc weights in transpiler * FC MKL-DNN: Update input pointer in re-used fc primitive * Add log for not handling fc fuse for unsupported dims test=develop * FC MKL-DNN: Move transpose from pass to Op Kernel test=develop * FC MKL-DNN: Disable transpose in unit test test=develop * FC MKL-DNN: Remove fc_mkldnn_pass from default list * Correct Flag for fake data analyzer tests test=develop * FC MKL-DNN: Add comment about fc mkldnn pass disablement test=develop * FC MKL-DNN: Disable fc in int8 tests test=develop	6 years ago
Sylwester Fraczek	5b2a3c4b12	Conv concat relu quantization (#17466) ... * add conv_concat_relu fuse test=develop * add test code test=develop * added missing include with unordered_map test=develop * review fixes for wojtuss test=develop * remove 'should (not) be fused' comment statements one of them was invalid anyway test=develop	6 years ago
Sylwester Fraczek	bccb0ba49a	fix quantize_squash_pass segfault when no tensor linked to Bias (#17292) ... * fix quantize_squash_pass segfault when there is no tensor linked do Bias input test=develop * add googlenet test test=develop * fix concat CreateKey not using input format test=develop	6 years ago
Zhaolong Xing	38da103034	fix trt ci bug temporary. (#17565) ... ban all trt ut. will fix it later. test=develop	6 years ago
lijianshe02	daf88968e2	fix bug that saved optimal model path in test_analyzer_save_model con… (#17555) ... * modify saved model path in analyzer_save_model.cc test=develop	6 years ago
guomingz	2281ebf0f3	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130) ... * Relu6 is the bottleneck op for Mobilenet-v2. As the mkldnn supports the conv/relu6 fusion, we implement it fusion via cpass way. Due to the int8 enabling for this fusion will be supported in MKLDNN v0.20, so this PR is focused on the fp32 optimization. Below table shows the benchmark(FPS) which measured on skx-8180(28 cores) Batch size | with fusion | without fusion -- | -- | -- 1 | 214.7 | 53.4 50 | 1219.727 | 137.280 test=develop * Fix the format issue test=develop * Add the missing nolint comments. test=develop * Fix the typos. test=develop * Register the conv_brelu_mkldnn_fuse_pass for the MKLDNN engine. test=develop * Adjust the indentation. test=develop * Add the test_conv_brelu_mkldnn_fuse_pass case. test=develop * Slightly update the code per Baidu comments. Let the parameter definition embedded into the code. That's will make the code easy to understand. test=develop	6 years ago
Tao Luo	3d19f44a89	remove unused SERIAL compiler option (#17500) ... test=develop	6 years ago
lidanqing	36757ed203	Enabling resnet101, vgg16, vgg19 INT8v2 model tests (#17468) ... * Add 6 models tests support in CMake * enabling resnet101, vgg16, vgg19 INT8v2 model tests test=develop * remove SERIAL test=develop	6 years ago
liuwei1031	ba70cc499e	fix security bugs : (#17464) ... http://newicafe.baidu.com:80/issue/PaddleSec-33/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-28/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-25/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-24/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-21/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-20/show?from=page test=develop	6 years ago
Tao Luo	32da5e9c3d	remove unused expected_kernel_cache_pass (#17486) ... test=develop	6 years ago
wopeizl	ca3ba378c7	fix the random compilation failure on windows test=develop (#17475) ... * fix the random compilation failure on windows	6 years ago
Zhen Wang	4a1b7fec96	Add setting Scope function for the graph class (#17417) ... * add set_not_owned function for graph * add scope set. test=develop * add scope_ptr enforce not null before setting.test=develop	6 years ago
flame	e48dd92fc8	bug fix (#17392) ... fix secure bug	6 years ago
Zhaolong Xing	7a3bb061d8	fix: (#17279) ... 1. infernce multi card occupy 2. facebox model inference occupy too much test=develop	6 years ago
Wojciech Uss	984aa90583	improved unit test output (#17266) ... added printing data type to differentiate int8 and fp32 latency results test=develop	6 years ago
石晓伟	a72dbe9abf	Cherry-pick benchmark related changes from release/1.4 (#17156) ... * cherry-pick commit from 8877054 * cherry-pick commit from 3f0b97d * cherry-pick from 16691:Anakin subgraph support yolo_v3 and faster-rcnn (cherry picked from commit 8643dbc233) * Cherry-Pick from 16662 : Anakin subgraph cpu support (cherry picked from commit 7ad182e16c) * Cherry-pick from 1662, 16797.. : add anakin int8 support (cherry picked from commit e14ab180fe) * Cherry-pick from 16813 : change singleton to graph RegistBlock test=release/1.4 (cherry picked from commit 4b9fa42307) * Cherry Pick : 16837 Support ShuffleNet and MobileNet-v2 Support ShuffleNet and MobileNet-v2, test=release/1.4 (cherry picked from commit a6fb066f90) * Cherry-pick : anakin subgraph add opt config layout argument #16846 test=release/1.4 (cherry picked from commit 8121b3eccb) * 1. add shuffle_channel_detect (cherry picked from commit 6efdea8997) * update shuffle_channel op convert, test=release/1.4 (cherry picked from commit e4726a066f) * Modify symbol export rules test=develop	6 years ago
Leo Zhao	54636a1982	call SetNumThreads everytime to avoid missing omp thread setting (#17224) ... * call SetNumThreads everytime to avoid missing omp thread setting resolve #17153 test=develop * add paddle_num_threads into config for test_analyzer_pyramid_dnn resolve #17153 test=develop	6 years ago
wopeizl	83c4f7721f	use two GPUs to run the exclusive test test=develop (#17187)	6 years ago
tensor-tang	79ed1c76cd	fix bn fuse vardesc and add model saver (#17143) ... * fix bn fuse vardesc and add model saver test=develop * unify save model in test helper test=develop * fix mkdir on windows test=develop * remove magic number use bn bias var desc test=develop	6 years ago
Tao Luo	d9cd989825	Merge pull request #17048 from luotao1/fix_runtime_cache_bug ... fix runtime_context_cache bug when gpu model has an op runs only on cpu	6 years ago
tangwei12	13295d90d9	load persistables with selected rows, test=develop (#17047)	6 years ago
luotao1	490e746269	fix runtime_context_cache bug when gpu model has an op runs only on cpu ... test=develop	6 years ago
wopeizl	d9991dccdd	add parallel build script to ci … (#16901) ... * add parallel build script to ci test=develop * 1. classify the test case as single card/two cards/multiple cards type 2. run test case according to the run type	6 years ago
Tao Luo	aa7b975bf6	disable runtime_context_cache pass by default ... test=develop	6 years ago
nhzlx	bc6b0ca1f4	fix trt anakin subgraph compile rely ... test=develop	6 years ago
gongweibao	cbdb8a17b1	Polish DGC code (#16818)	6 years ago
Tao Luo	bc037c13c7	use multi-thread to speedup CI tests ... test=develop	6 years ago
Tao Luo	5b1565a7be	Merge pull request #16875 from lidanqing-intel/lidanqing/improve_preprocess_script ... Improve preprocessing script and read from tar	6 years ago
root	1965a22488	minus trt ci times. ... test=develop	6 years ago
Tao Luo	ca8b8fa0bd	Merge pull request #16830 from Superjomn/fix/tmp-memory-optim ... fix memory optim temporarily	6 years ago
lijianshe02	de26df440b	add SaveOptimModel interface in analysis_predictor.h and test it in a… (#16441) ... * add SaveOptimModel interface in analysis_predictor.h and test it in analyzer_dam_tester and analyzer_resnet50_tester test=develop	6 years ago
lidanqing	de02d40e98	improve preprocess script and read from tar ... test=develop	6 years ago
superjomn	f58c3ec189	fix memory optim temporarily ... test=develop	6 years ago
Yihua Xu	93cedfdb9c	Fix the order while sorting the operators (#16756) ... * Fix the order when sorting operators. test=develop * Enable transfomer compare test item. test=develop * Use set to replace vector. test=develop	6 years ago
liuwei1031	85363848a1	Security issue (#16774) ... * disable memory_optimize and inpalce strategy by default, test=develop * fix security issue http://newicafe.baidu.com:80/issue/PaddleSec-3/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-8/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-12/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-32/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-35/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-37/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-40/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-43/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-44/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-45/show?from=page test=develop * revert piece.cc, test=develop * adjust api.cc,test=develop	6 years ago
tensor-tang	d6c1b5a73b	disable seqpool concat pass by default saving CI time ... test=develop	6 years ago
Tao Luo	ad4a1bd13c	Merge pull request #16339 from luotao1/core_opt_choose_kernel ... Cache the chosen kernel of operators	6 years ago
Tao Luo	d5c8d4acfe	reduce all analyzer_test ci elasped time ... test=develop	6 years ago
luotao1	226596a296	Merge branch 'develop' into core_opt_choose_kernel	6 years ago
bingyanghuang	88ceda5134	MKLDNN INT8 v2 readme.md (#16515)	6 years ago
luotao1	bd636a9ea6	test_analyzer_int8 tests use default pass order ... test=develop	6 years ago
Yan Chunwei	044ae2497d	fix identity temporarily (#15942)	6 years ago
Wojciech Uss	ec2750b3c2	fix repeating passes (#16606)	6 years ago
Wojciech Uss	9b6a029666	fix dataset reading and add support for full dataset (#16559)	6 years ago
lidanqing	2ca0de3cd4	fix preprocess script with processbar, integrity check and logs (#16608) ... * fix preprocess script with processbar, integrity check and logs test=develop * delete unnecessary empty lines, change function name test=develop	6 years ago
Tao Luo	ce18710421	enhance analyzer_tests download ... test=develop	6 years ago
石晓伟	5dea0bdd1b	Merge pull request #16498 from Shixiaowei02/feature/anakin-engine ... merge feature/anakin-engine to develop	6 years ago
Shixiaowei02	7b9fc71076	update tensorrt subgraph_util test=develop	6 years ago
Wojciech Uss	2498395132	remove profiling from int8 test ... test=develop	6 years ago
Zhaolong Xing	3e6aa498d6	Merge pull request #16526 from NHZlX/refine_trt_anakin ... refine subgraph trt and anakin	6 years ago
Tao Luo	8f7b5883b8	Merge pull request #16529 from lidanqing-intel/lidanqing/preprocess-data ... preprocess with PIL the full val dataset and save binary	6 years ago
Tao Luo	5b24002389	Merge pull request #16399 from sfraczek/sfraczek/analyzer_int8_resnet50_test ... create test for quantized resnet50	6 years ago
Shixiaowei02	bddb2cd315	resolve conflicts with the develop branch test=develop	6 years ago
lidanqing	0d656996bf	fix some bugs of unzip and reading val list ... test=develop	6 years ago
nhzlx	d065b5bf2b	Anakin ssd support ... refine trt first run add quant dequant fuse pass omit simplify_anakin_priorbox_detection template omit transpose_flatten_concat_fuse template test=develop	6 years ago
lidanqing	b46e467abc	add wget and unzip part and change data_dir ... test=develop	6 years ago
lidanqing	894aa9b235	change script file name and data_dir location ... test=develop	6 years ago
lidanqing	57f51e5b08	preprocess with PIL the full val dataset and save binary ... test=develop	6 years ago
chengduo	ed61d67c73	Fix the interface of Pass::Apply (#16484) ... * modify the interface of Pass::Allay test=develop * Polish code test=develop * Fix Travis CI test=develop * fix Pass::Apply interface test=develop * Fix Travis CI test=develop	6 years ago
Sylwester Fraczek	8ece7a9708	fixed url to dataset ... test=develop	6 years ago
gongweibao	eb83abeac3	Add DGC(Deep Gradient Compression) interface. (#15841)	6 years ago
Sylwester Fraczek	fe21578a44	create test for quantized resnet50 ... test=develop	6 years ago
Michał Gallus	2d8b7b3a76	Refine default MKL-DNN Pass order (#16490) ... * Refine default MKL-DNN Pass order test=develop * Add comment to default MKL-DNN Pass list test=develop	6 years ago
Wojciech Uss	09dfc7a2aa	C-API quantization core 2 (#16396) ... * C-API quantization core test=develop Co-authored-by: Sylwester Fraczek <sylwester.fraczek@intel.com> * Decouple Quantizer from AnalysisPredictor test=develop * fixes after review test=develop * renamed mkldnn quantize stuff test=develop * remove ifdef from header file test=develop	6 years ago
Yihua Xu	57dc3c1943	Disable compare for Issue#16316 (#16466) ... * Disable compare for accuracy issue. test=develop * Add todo comments to show more information. test=develop	6 years ago
nhzlx	953bdde058	Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD ... test=develop	6 years ago
nhzlx	45b3766fdf	fix comments ... test=develop	6 years ago
Wojciech Uss	46677fb080	Move cpu_quantize_* passes into mkldnn subfolder ... test=develop	6 years ago
liuwei1031	de3b70a101	fix cdn issue, test=develop (#16423) ... * fix cdn issue, test=develop * fix cdn issue, test=develop	6 years ago
nhzlx	3df7b98a0f	Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD	6 years ago
nhzlx	f3a2e4b3d8	1. Add ANAKIN_ROOT compile option ... 2. refine trt code test=develop	6 years ago
Tao Luo	294cdf6f48	Merge pull request #16177 from fc500110/remove_visualizer ... remove graph visualizer tool, which can be replaced by python IrGraph draw API	6 years ago
luotao1	056599a738	add expected_kernel_cache_pass ... test=develop	6 years ago
Wojciech Uss	cbe2dbf0db	Add enabling quantization (#16326) ... * Add enabling quantization test=develop * remove unused (here) function	6 years ago
nhzlx	4f4daa4b66	cherry-pick from feature/anakin-engine: add data type for zero copy #16313 ... 1. refine anakin engine 2. add data type for zero copy align dev branch and PaddlePaddle:feature/anakin-engine brach the cudnn workspace modify was not included for now, because we use a hard code way in feature/anakin-engine branch. There should be a better way to implement it, and subsequent submissions will be made. test=develop	6 years ago
nhzlx	07dcf2856c	git cherry-pick from feature/anakin-engine: update anakin subgraph #16278	6 years ago
nhzlx	c407dfa3cb	cherry-pick from feature/anakin-engine: refine paddle-anakin to new interface. #16276	6 years ago
nhzlx	a25331bc26	cherry-pick from feature/anakin-engine: deal the changing shape when using anakin #16189	6 years ago
nhzlx	c79f06d3d8	cherry-pick from feature/anakin-engine: add batch interface for pd-anakin #16178	6 years ago
nhzlx	69d37f81d7	cherry-pick from feature/anakin-engine: refine anakin subgraph. #16157 ... support change input size	6 years ago
nhzlx	a1d200a5de	cherry-pick from feature/anakin-engine: Anakin support facebox #16111	6 years ago
flame	a32d420043	cherry-pick from feature/anakin-engine: batch norm (#16110) ... * use anakin batch norm and scale implement fluid batch norm	6 years ago
flame	0945b97f07	cherry-pick feature/anakin-engine: add anakin softmax/transpose/batch_norm/flatten/reshape op (#16020) ... * add anakin softmax/ flatten/reshape/transpose/batch_norm op converter	6 years ago